3D Vehicle Detection Using Camera and Low-Resolution LiDAR

Nowadays, Light Detection And Ranging (LiDAR) has been widely used in autonomous vehicles for perception and localization. However, the cost of a high-resolution LiDAR is still prohibitively expensive, while its low-resolution counterpart is much more affordable. Therefore, using low-resolution LiDAR for autonomous driving perception tasks instead of high-resolution LiDAR is an economically feasible solution. In this paper, we propose a novel framework for 3D object detection in Bird-Eye View (BEV) using a low-resolution LiDAR and a monocular camera. Taking the low-resolution LiDAR point cloud and the monocular image as input, our depth completion network is able to produce dense point cloud that is subsequently processed by a voxel-based network for 3D object detection. Evaluated with KITTI dataset, the experimental results shows that the proposed approach performs significantly better than directly applying the 16-line LiDAR point cloud for object detection. For both easy and moderate cases, our detection results are comparable to those from 64-line high-resolution LiDAR. The network architecture and performance evaluations are analyzed in detail.

[1]  Mohamed ElHelw,et al.  Improved Semantic Segmentation of Low-Resolution 3D Point Clouds Using Supervised Domain Adaptation , 2020, 2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES).

[2]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[3]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[4]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[5]  Xinming Huang,et al.  Real-Time Road Segmentation Using LiDAR Data Processing on an FPGA , 2017, 2018 IEEE International Symposium on Circuits and Systems (ISCAS).

[6]  Bin Yang,et al.  PIXOR: Real-time 3D Object Detection from Point Clouds , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Francesc Moreno-Noguer,et al.  Low Resolution Lidar-Based Multi-Object Tracking for Driving Applications , 2017, ROBOT.

[8]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[9]  Santiago Velasco-Forero,et al.  Road Segmentation on low resolution Lidar point clouds for autonomous vehicles , 2020, ArXiv.

[10]  Fahimeh Farahnakian,et al.  Fusing LiDAR and Color Imagery for Object Detection using Convolutional Neural Networks , 2020, 2020 IEEE 23rd International Conference on Information Fusion (FUSION).

[11]  Lennart Svensson,et al.  Fast LIDAR-based road detection using fully convolutional neural networks , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[12]  Hayder Radha,et al.  CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection , 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[13]  Alejandro Barrera,et al.  BirdNet+: End-to-End 3D Object Detection in LiDAR Bird’s Eye View , 2020, 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC).

[14]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Sertac Karaman,et al.  Self-Supervised Sparse-to-Dense: Self-Supervised Depth Completion from LiDAR and Monocular Camera , 2018, 2019 International Conference on Robotics and Automation (ICRA).

[16]  Yan Wang,et al.  End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Thomas B. Moeslund,et al.  Deep car detection by fusing grayscale image and weighted upsampled LiDAR depth , 2021, International Conference on Machine Vision.

[18]  Junxuan Zhao,et al.  Automatic Vehicle Tracking With Roadside LiDAR Data for the Connected-Vehicles System , 2019, IEEE Intelligent Systems.